review-change

Review a change.

Quality

25%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./internal/preserve/testdata/markdown-existing/package/skills/review-change/SKILL.md

Quality

Content

26%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content body is essentially empty — just a heading restating the skill name — so it provides no actionable guidance, no workflow, and no navigable structure. Its only virtue is the absence of padding, which keeps conciseness high while every substantive dimension scores at the bottom.

Suggestions

Add a concrete workflow: how to obtain the diff (`git diff`/`gh pr diff`), what to inspect, and how to present findings.

Include at least one runnable example, e.g. a command to view the change and a template for the review summary.

Add validation/verification steps (confirm tests pass, check for destructive edits) since review involves assessing risky changes; their absence caps workflow clarity at 3.

Dimension	Reasoning	Score
Conciseness	The body ("# Review change") has no padding or over-explanation whatsoever — it is maximally lean on the token-bloat axis the conciseness rubric measures, fitting the "efficient, no over-explanation" anchor 4 rather than the verbose low anchors.	4 / 5
Actionability	The body contains only a heading with no concrete code, commands, or steps, matching the "entirely vague or abstract; no concrete code or commands" anchor 1.	1 / 5
Workflow Clarity	There is no sequence of steps, no checkpoints, and no validation whatsoever — just a title — matching the "steps missing or incoherent; no sequence" anchor 1.	1 / 5
Progressive Disclosure	The body offers only a single heading with no content, no references, and nothing to navigate or organize; it is a degenerate near-empty case that sits at the minimal-structure anchor 2.	2 / 5
	Total	8 / 20 Passed

Description

25%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is uniformly vague: it names a domain and one generic action but provides no trigger guidance, no synonyms, and no concrete specifics, leaving it indistinct from many other review skills. Every dimension lands at the low-anchor end of the scale.

Suggestions

State concrete actions the skill performs, e.g. "Reads a git diff, summarizes changed files, and flags risky edits for human review."

Add an explicit trigger clause: "Use when the user asks to review a change, diff, pull request, or staged changes."

Narrow the domain to reduce conflict risk, e.g. scoping to code/git changes and naming file types like .diff or PR numbers.

Dimension	Reasoning	Score
Specificity	"Review a change." names a domain ("change") and a single generic action ("Review"), sitting between the entirely-vague anchor 1 and the names-domain anchor 2; it is closer to anchor 2 because it has a real action verb, but lacks any concrete specifics.	2 / 5
Completeness	It offers a vague "what" ("review a change") and no "when" guidance at all; the missing "Use when..." clause caps completeness at 3, and the vague what pulls it down to anchor 2.	2 / 5
Trigger Term Quality	Only two generic keywords ("review", "change") with no natural variations or synonyms (diff, PR, patch) and no explicit "Use when..." framing, matching the "one or two generic keywords" anchor 2.	2 / 5
Distinctiveness Conflict Risk	"Review a change" is very broad and could plausibly trigger code-review, document-review, or any review skill, giving high overlap risk consistent with anchor 2.	2 / 5
	Total	8 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
description_field	'description' is very short (16 chars), consider making it more detailed	Warning

	Total	15 / 16 Passed

Repository: jbaruch/agentic-context-registry
Path: internal/preserve/testdata/markdown-existing/package/skills/review-change/SKILL.md
Commit: 788cdf0

Reviewed: ~7 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.